INDEX

Explanations

references to realization and understanding of truths or important concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phan

-0.17

?url

-0.14

@brief

-0.14

ÐµÑģÑĮ

-0.14

owers

-0.13

uest

-0.13

 ä½į

-0.13

Ø³Ø·

-0.13

ondon

-0.13

POSITIVE LOGITS

rung

0.16

assi

0.15

ra

0.14

raft

0.14

æŀ

0.14

ei

0.14

zers

0.14

Activations Density 0.095%

references to realization and understanding of truths or important concepts

No Comments

No Known Activations